The advances in automotive technology continue to deliver safety and driving comfort benefits to the society. The Automated Driving Assistance System (ADAS) technology is at the forefront of this evolution. Today, various vehicle models on the road have features like lane keeping assist, lane centering, automated emergency braking, adaptive cruise control, traffic jam assist etc. During early development, such feature algorithms often assume ideal environmental and vehicle conditions while doing a performance evaluation. This study focuses on the use of simulation platform to evaluate robustness of the lane centering ADAS feature in presence of various factor variations. The feature considered here is an end-to-end feature, i.e., from camera sensor output to steering actuation. The use of closed-loop simulation tools is well recognized in automotive industry for early requirements validation as well as robustness study. However, it has been traditionally used mainly for vehicle actuator controls rather than ADAS features. For our study, variations such as road geometry, vehicle loading, steering bias etc. are considered. The performance metric of the lane centering feature is presented, for the base case as well as in the presence of these variations, to highlight real life challenges encountered while developing such feature algorithms. Furthermore, some control algorithm modification is suggested to reduce such variation where necessary. This study will help understand impact of variations on algorithm performance, and how to use the simulation tools to understand as well as tackle such challenges.